This is the Factory5 team, a Russian software developer for industrial enterprises. Many people now use the phrase “digital twin”, sometimes not knowing what it is. Today, together with the product manager, we will explain what the digital twin really means and why it is not always needed.
What is a digital twin?
A digital twin is a virtual copy of a real object that behaves in the same way as a real object. It reflects in real time all processes occurring with a physical object. The error between the operation of the virtual model and what happens in reality should not exceed 5%.
The digital twin combines a large amount of information from different sources. Therefore, the most detailed version of the twin contains data on the appearance of the object, its functions, state, external interventions and much more.
For example, Tecnomatix created a digital production twin for PROLIM who wanted to improve the picking process. To begin with, a visual production twin was created. Further, data was taken from the sensors on the speed of movement of objects, the number of workers and their performance, and many others. All this information made it possible to create a digital twin that repeats all the processes of a real object.
The video shows how you can change different production parameters and test other conditions. For example, the number of workers in the picking shop.
Thus, the more different data there is about a physical object, the easier it is to create a digital copy of it and the more detailed it will be.
What he really is?
It is a program created on the basis of 3D technologies, VR or AR, as well as AI and IoT at the same time. The result of the synergy of several complex technologies and fundamental sciences. Most often, it reflects the visual representation of a physical object and, ideally, repeats the process of work in the finest detail. All physical, technological and business processes are described using mathematics. And to make it dynamic, the Internet of Things (IoT) comes to the rescue: sensors built into the object transmit information about the current state of the object in real time. And this is reflected in the digital twin.
Why are digital twins useful?
You can put any experiments on them. When any conditions are introduced, the double reacts in the same way as a real physical object would react to it. Therefore, you can evaluate its capabilities, check your expectations, play several scenarios for the development of events and choose the most optimal one.
However, the digital twin requires a huge investment. Even creating a twin of an object fully equipped with sensors requires a large multidisciplinary team and colossal capabilities to collect and store big data. Only those who want to be like Iron Man need such a "pure" digital twin.
How to replace the digital twin?
Small and medium-sized companies will only need a digital model or a 3D model, which, unlike a twin, is static and does not reflect the state of the object in real time. Or vice versa, a detailed reflection of the current state of the object on a rather schematic visual series.
Depending on the tasks to be solved, it is worth concentrating on those parameters that are really important in the model. For example, in interior design, it is more important to look at how the colors and textures of materials will combine in the same room. And in training pilots on an airplane simulator, it is more important to recreate the possible flight conditions and technical features of the machine. This approach means that you use 20% of the effort to achieve 80% of the results. For significantly less money.
Our experience
At Factory5, we have created the F5 PMM solution for predicting the technical condition of industrial equipment . From the point of view of digital modeling, it reflects the main components of the equipment, which especially need to predict failures. This is clarified at the stage of the pre-project survey and when drawing up expert rules. The nodes are displayed in detail on a 2D model for clarity and expanding expertise: this way not only the first-class engineer understands where the anomaly occurs, but any employee.
We will tell you about how similar models for equipment are developed in the following blog materials.